Using consumer behavior data to reduce energy consumption in smart homes

TL;DR

This paper introduces a frequent pattern mining algorithm tailored for smart home data, enabling autonomous energy-saving recommendations based on user behavior, validated through real-world deployment and user feedback.

Contribution

A novel sequential pattern mining algorithm for smart home data and a recommender system that adapts based on user feedback to improve energy savings.

Findings

Algorithm outperforms existing methods in run time and memory efficiency.

Recommender system effectively influences user behavior towards energy savings.

User feedback improves recommendation accuracy over time.

Abstract

This paper discusses how usage patterns and preferences of inhabitants can be learned efficiently to allow smart homes to autonomously achieve energy savings. We propose a frequent sequential pattern mining algorithm suitable for real-life smart home event data. The performance of the proposed algorithm is compared to existing algorithms regarding completeness/correctness of the results, run times as well as memory consumption and elaborates on the shortcomings of the different solutions. We also present a recommender system based on the developed algorithm that provides recommendations to the users to reduce their energy consumption. The recommender system was deployed to a set of test homes. The test participants rated the impact of the recommendations on their comfort. We used this feedback to adjust the system parameters and make it more accurate during a second test phase.